主题图谱 / audio and speech processing

audio and speech processing

GeneTech 知识引擎共收录 461 篇相关科研实体，横跨 30 个垂直领域。数据来自 OpenAlex、arXiv、Crossref、PubMed、Europe PMC 等公开学术源，全部可溯源到原文。

年度产出趋势

相关主题

代表性文献（按质量分排序，前 60 条）

• EEG-based brain-computer interface (BCI) dataset for directional word recognition.
  2026 · 仿生智能 · We present an EEG dataset recorded from 22 neurologically healthy volunteers (12 native Russian speakers and 10 native Spanish speakers) during overt and covert articulation of six spatial-direction words. Monopolar EEG …
• Fusion Guard: A Multi-Scale Sequential Fusion Framework for Small Target Detection in Unmanned Aerial Vehicle Scenarios Using YOLO-World
  2025 · 低空经济 · Abstract This paper presents a multi-scale sequence fusion framework, Fusion Guard, built upon YOLO-World to enhance small target detection from UAV scenarios. To overcome the limitations of traditional models in feature…
• Retraction Notice: Smart Farming: An automatic water irrigation and animal detection model
  2026 · 智慧农业 · Agriculture activities have become smart enough t o assist farmers by developing automatic water irrigation and animal detection models. The proposed system assists them in both the fields and in the sale of the product …
• Semantic Segmentation Algorithm Based on Semantic Flow Alignment Network
  2026 · AI 安全与对齐 · To address the decline in indoor visual localization and navigation performance caused by pedestrian occlusions, this paper proposes a semantic segmentation algorithm based on semantic flow alignment network. The algorit…
• Model checkpoints for paper FakeMark: Deepfake Speech Attribution With Watermarked Artifacts
  2026 · AI 驱动科学发现 · README This repository contains the model checkpoints for our paper FakeMark: Deepfake Speech Attribution With Watermarked ArtifactsWanying Ge, Xin Wang, Junichi Yamagishi.The Authenticity & Provenance in the Age of AI W…
• Model checkpoints for paper FakeMark: Deepfake Speech Attribution With Watermarked Artifacts
  2026 · AI 驱动科学发现 · README This repository contains the model checkpoints for our paper FakeMark: Deepfake Speech Attribution With Watermarked ArtifactsWanying Ge, Xin Wang, Junichi Yamagishi.The Authenticity & Provenance in the Age of AI W…
• Enhancing Arabic Speech Therapy with AI: A Specialized AI-Based System for Arabic Stuttering Classification
  2026 · AI 驱动科学发现 · The phenomenon of stuttering and its associated speech disorders disrupt fluency through repetition, prolongation, and delay, affecting millions of people. Although considerable progress has been made in artificial intel…
• Intelligent Optimization of Digital Human Generation via Edge-Adaptive Interpolation and Preference-Enhanced Speech Synthesis
  2026 · 边缘智能 · This paper presents a digital human generation method that combines an adaptive image interpolation algorithm with controllable text-to-speech (TTS) technology. To address digital human image blurring, we employ an edge …
• Machine-learning-based approaches for predicting child mortality
  2026 · 边缘智能 · Historically, the rate of child mortality has served as a gauge of a country’s overall level of development. The international community has been setting periodic targets to reduce child mortality over the past 20 years.…
• Myoelectric Control based on Machine Learning of a Low-Cost 7-DOF Transhumeral Prosthetic Arm through TinyML
  2026 · 边缘智能 · Upper-limb amputations are a significant source of disability, especially in resource-limited environments where expensive commercial-grade prosthetics (often costing over USD 70,000) are unaffordable. This paper describ…
• Synchronization of Speech and Lip Motion with a Service Humanoid Robot
  2026 · 具身智能 · With the increasing deployment of humanoid service robots in presentation and narration scenarios, there is a growing demand for more natural and effective interactive capabilities. To enhance the expressiveness and moti…
• AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic Documents
  2026 · 具身智能 · We present ANANDASKY, a vision-language model for line-level transcription of historical sinographic documents.The model combines a compact high-resolution visual encoder with global attention, 10 px patches, uncompresse…
• A Unified Hybrid Encoder–Decoder Model for Vision–Language Image Captioning
  2026 · 具身智能 · Abstract Image captioning is a combined activity that generates relevant text descriptions of images using natural language processing and computer vision. The outcomes are heavily influenced on the supplied image’s qual…
• Individual Propeller Source Noise Assessment from Full-Scale eVTOL Flight Test Measurements
  2026 · 低空经济 · Aircraft equipped with distributed propulsion, e.g., those utilizing many propulsors for lift and thrust, radiate complex acoustic signatures with strong dependence on the vehicle state. In an effort to better interpret …
• IEA-Plugin: An AI Agent Reasoner for Test Data Analytics
  2025 · AI Agent 生态 · This paper introduces IEA-plugin, a novel AI agent-based reasoning module developed as a new front-end for the Intelligent Engineering Assistant (IEA). The primary objective of IEA-plugin is to utilize the advanced reaso…
• ApexCodium: a Multi-Agent System for Code Generation with Enhanced Self-Reflection
  2025 · AI Agent 生态 · LLMs demonstrate a remarkable performance on natural language tasks, but they are relatively less accurate when it comes to code generation. This gap stems from the inherent complexity of coding, which demands precise lo…
• Real-Time Pest Detection System Using Efficientnet Deployed On Raspberry Pi For Precision Agriculture
  2025 · 智慧农业 · A real-time pest classification system is developed for this study with the help of Efficient Net architecture for precision as well as for resource efficiency. The hardware setup includes a Raspberry Pi 4 Model B, 4 GB …
• Metabolic maps from hyperspectral data for precision grape maturation and decision-making
  2025 · 智慧农业 · This study applied a tomography-like (TL) method to assess the physicochemical properties of grapes in the Douro Wine Region, in the skin, pulp and seed, focusing on soluble solids content (SSC), chlorophyll (CHL), and a…
• Precision Detection of Small Brown Planthoppers in Agriculture via YOLOv8 Fine-Tuning
  2025 · 智慧农业 · The research evaluates the quality of the YOLOv8 architecture in terms of its efficiency in the fine-tuning scenario when it comes to detecting small objects, and the Brown Planthopper (BPH) in a farming setting will be …
• Attention-assisted dual-branch interactive face super-resolution network
  2025 · 智慧农业 · We propose a deep learning-based Attention-Assisted Dual-Branch Interactive Network (ADBINet) to improve facial super-resolution by addressing key challenges like inadequate feature extraction and poor multi-scale inform…
• Transformer-based fusion model for mild depression recognition with EEG and pupil area signals
  2025 · 生物计算 · Early detection and treatment are crucial for the prevention and treatment of depression; compared with major depression, current researches pay less attention to mild depression. Meanwhile, analysis of multimodal biosig…
• Across-speaker articulatory reconstruction from sensorimotor cortex for generalizable brain-computer interfaces
  2025 · 仿生智能 · Abstract Objective Speech brain-computer interfaces (BCIs) can restore speech features like articulatory movements from brain activity. However, for individuals with vocal tract paralysis, lack of articulatory movements …
• Design of Digital Twin-Based Digital Signage Advertisement Platform
  2025 · 数字孪生 · This paper presents a digital twin-based digital signage platform designed to improve the accuracy of advertising effectiveness measurement and introduce new content switching methods. By utilizing real-time pedestrian d…
• Real-Time Subtitle Generation for Live Videos Using AI and Machine Learning
  2025 · 边缘智能 · Real-time subtitling of live video streams is still a major challenge because of the difficulties involved in processing spontaneous speech, dealing with multiple speakers, and coping with varying audio conditions with l…
• DeCGAN: Speech Enhancement Algorithm for Air Traffic Control
  2025 · 低空经济 · Air traffic control (ATC) communication is susceptible to speech noise interference, which undermines the quality of civil aviation speech. To resolve this problem, we propose a speech enhancement model, termed DeCGAN, b…
• A dual-cutoff machine-learned potential for condensed organic systems obtained <i>via</i> uncertainty-guided active learning.
  2024 · AI 驱动科学发现 · Machine-learned potentials (MLPs) trained on ab initio data combine the computational efficiency of classical interatomic potentials with the accuracy and generality of the first-principles method used in the creation of…
• TSTA: Thread and SIMD-Based Trapezoidal Pairwise/Multiple Sequence Alignment Method
  2024 · AI 安全与对齐 · Abstracts The rapid advancements in sequencing length necessitate the adoption of increasingly efficient sequence alignment algorithms. The Needleman-Wunsch method introduces the foundational dynamic programming (DP) mat…
• CLASP: Cross-modal Alignment Using Pre-trained Unimodal Models
  2024 · AI 安全与对齐 · Recent advancements in joint speech-text pretraining have significantly advanced the processing of natural language.However, a key limitation is their reliance on parallel speechtext data, posing challenges due to data a…
• Underwater Fuzzy Image Enhancement Method Based on CycleGAN
  2024 · 深海科技 · In order to addressing color inaccuracies and insufficient contrast in submerged photography caused by light absorption and scattering effects, this paper presents an enhanced image enhancement methodology based on a mod…
• Multimodal Recognition of Landmarks Based on Vision Language Model
  2024 · 具身智能 · In the task of landmark recognition, the recognition accuracy is easily affected by factors such as lighting, angle, and season. Existing landmark recognition methods have poor ability to understand deep semantics and ca…
• Few-shot generative model for skeleton-based human action synthesis using cross-domain adversarial learning
  2024 · 具身智能 · We propose few-shot generative models of skeleton-based human actions on limited samples of the target domain. We exploit large public datasets as a source of motion variations by introducing novel cross-domain and entro…
• Divide and Conquer Boosting for Enhanced Traffic Safety Description and Analysis with Large Vision Language Model
  2024 · 具身智能 · The increasing complexity of traffic dynamics has underscored the necessity for advanced traffic safety description and analysis, challenging the efficacy of current methodologies in comprehensively understanding and pre…
• Context-aware Emotion Recognition Based on Vision-Language Pre-trained Model
  2024 · 具身智能 · Given the difficulty of recognizing ambiguous emotions in facial expression recognition tasks, we propose a visual-language model named CAER-CLIP to address this challenge. The proposed CAER-CLIP standed for Context-Awar…
• SheffieldVeraAI at SemEval-2024 Task 4: Prompting and fine-tuning a Large Vision-Language Model for Binary Classification of Persuasion Techniques in Memes
  2024 · 具身智能 · This paper describes our approach for SemEval-2024 Task 4: Multilingual Detection of Persuasion Techniques in Memes.Specifically, we concentrate on Subtask 2b, a binary classification challenge that entails categorizing …
• Sonic VisionLM: Playing Sound with Vision Language Models
  2024 · 具身智能 · There has been a growing interest in the task of generating sound for silent videos, primarily because of its prac-ticality in streamlining video post-production. However, existing methods for video-sound generation atte…
• Multi-level supervised vision language model based steel surface defect detection
  2024 · 具身智能 · The shape of defects on steel surfaces is highly variable and training samples are limited, making it a significant challenge to transfer a high-performance pretrained vision language model to steel surface defect detect…
• Improved Faster Region-Based Convolutional Neural Networks (R-CNN) Model Based on Split Attention for the Detection of Safflower Filaments in Natural Environments
  2023 · 智慧农业 · The accurate acquisition of safflower filament information is the prerequisite for robotic picking operations. To detect safflower filaments accurately in different illumination, branch and leaf occlusion, and weather co…
• Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment
  2023 · AI 安全与对齐 · This paper presents a novel task, zero-shot voice conversion based on face images (zero-shot FaceVC), which aims at converting the voice characteristics of an utterance from any source speaker to a newly coming target sp…
• Player detection method based on scale attention and scale equalization algorithm
  2023 · 仿生智能 · Introduction Object detection methods for team ball games players often struggle due to their reliance on dataset scale statistics, resulting in missed detections for players with smaller bounding boxes and reduced accur…
• LimitAccess: on-device TinyML based robust speech recognition and age classification
  2023 · 边缘智能 · Abstract Automakers from Honda to Lamborghini are incorporating voice interaction technology into their vehicles to improve the user experience and offer value-added services. Speech recognition systems are a key compone…
• Analisis Gaya Kepemimpinan Demokratis, Transformasional, dan Situasional dalam Menghadapi Era Society 5.0
  2026 · AI 安全与对齐 · This study aims to analyze democratic, transformational and situational leadership styles in facing the era of society 5.0. using qualitative research methods using secondary data to analyze research literature reviews f…
• Real-Time Speech Denoising on Edge Devices for Disaster Response
  2026 · 边缘智能 · In disaster-affected areas, efficient communication is severely hindered by excessive ambient noise. This study presents a lightweight, deep learning-based speech denoising system designed to restore speech clarity under…
• A Comparative Analysis of Music Genre Classification via Tree-based Ensemble Learning Algorithms
  2026 · 边缘智能 · Music Genre Classification (MGC) is a fundamental task in music information retrieval, aiming to automatically assign a genre label to an audio track based on its audio characteristics. This paper presents a comparative …
• Deep learning models and speech data augmentation technologies for foreign language speech recognition
  2026 · 边缘智能 · Aiming at the problems of limited speech sample size, significant pronunciation differences and interference from complex environments in foreign language speech recognition, a foreign language speech recognition method …
• MathExpr-DETR: An RT-DETR-Based Deep Learning Algorithm for Tiny Target Detection of Mathematical Expressions
  2026 · 边缘智能 · Mathematical expression detection is a fundamental task in document analysis. To address the missed detection and inefficiency of tiny mathematical expression targets, this paper proposes MathExpr-DETR, built on the RT-D…
• TinyML-Based Speech Emotion Recognition on Microcontrollers Using Quantized CNNs and Mel-Filterbank Energy Features
  2026 · 边缘智能 · This paper presents a real-time, resource-efficient Speech Emotion Recognition (SER) system trained on a modified version of the Toronto Emotional Speech Set (TESS) that includes both male and female voice samples for fi…
• A method for selecting prosodic units in Tibetan based on function word features
  2026 · 具身智能 · Prosodic features are the key to the naturalness of speech synthesis, and the selection and division of their units mainly rely on the prosodic structure model. The study of prosody in Lhasa Tibetan is still in its infan…
• Dialectmind@DravidianLang Tech 2026: Zero-Shot Dialectal Tamil Automatic Speech Recognition Using a Large Pretrained Conformer Model
  2026 · 具身智能 · The low-resource dialectal Automatic Speech Recognition (ASR) in languages like Tamil is a critical issue because of phonological differences, lack of labeled data and because of the differences in the acoustic of speech…
• Substitution Matrices
  2026 · 基因技术工具 · This chapter introduces substitution matrices by explaining matrix notation and showing how bioinformaticians use evolutionary models to score amino acid similarities. It presents the development of point accepted mutati…
• Using AI Models to Detect and Combat Fake News
  2025 · AI 驱动科学发现 · The spread of fake news and misinformation has become a global challenge, undermining public trust, causing political polarization, and facilitating the dissemination of harmful ideologies. This study explores the use of…
• Welcome to AI Matters 10(3)
  2025 · AI 驱动科学发现 · Welcome to the third issue of this year's AI Matters Newsletter. The issue will start with a report by Dr. Louise A. Dennis summarizing recent conference events. We then welcome the article titled "AI-Oracle Machines for…
• An Artificial Intelligence-Driven Approach to Optimizing Digital Art Generation Models
  2025 · 医疗人工智能 · In order to solve the problem of the lack of annotated image data languages, AI-driven digital art generation model optimization methods are proposed. In this paper, we study Multilingual TTI (MTTI) and the current neura…
• The Ship Edge Detection based on High and Low Thresholds Method
  2025 · 边缘智能 · In order to lessen the decline in the accuracy of ship edge detection caused by the noise produced during the acquisition of remote-sensing images, This paper introduces ship detection technique utilizing significance of…
• An Artificial Intelligence-Driven Approach to Optimizing Digital Art Generation Models
  2025 · 边缘智能 · In order to solve the problem of the lack of annotated image data languages, AI-driven digital art generation model optimization methods are proposed. In this paper, we study Multilingual TTI (MTTI) and the current neura…
• Improved Detail Enhancement Based on Mamba and Edge-Guided Polyp Segmentation Model
  2025 · 边缘智能 · In early colorectal cancer screening, colonoscopic images are generally used for automated polyp segmentation and detection in order to improve diagnostic accuracy and efficiency. Automated segmentation of polyps remains…
• Multi-task learning for audio scene source counting and analysis
  2025 · 边缘智能 · Audio source counting is a fundamental task of audio scene analysis related to other audio tasks such as speaker diarization and sound event detection. It is also a relatively unexplored audio task that presents a comple…
• Bimodal Biometric Human Recognition System Using Deep Learning Algorithm
  2025 · 边缘智能 · Biometric recognition system combining two or more traits is a method of identifying human using deep learning techniques. Protection is the primary issue for humans nowadays. Biometric human identification system using …
• Estimating the hydrogen bond strength by machine learning approaches
  2025 · 边缘智能 · The capabilities of regression models was investigated to predict the hydrogen bond energy based on partial charges, bond orders, bond distances and element types. Support vector regression in combination with gradient b…
• Smart Plant Watering Using TinyML: Water Savings through Predictive Control
  2025 · 边缘智能 · Indoor plant watering is not always effective - people often overwater or underwater plants, wasting water and harming plant health. In view of this, a smart watering system using artificial intelligence that runs on a t…
• PersASR: A 2.3-μJ/frame 96.8%-accurate TinyML Automatic Speech Recognition Processor with Data Augmentation-Driven Personalization in 16-nm FinFET
  2026 · 边缘智能 · We present PersASR, a 16-nm FinFET personalized ASR processor that features on-chip retraining with hardware-efficient data augmentation and a hardware-optimized beam search. PersASR achieves a state-of-the-art ASR accur…

以 API 获取该主题全量数据

# 主题词表（含本主题的站点分布与年度分布）
curl https://data.swarmlabs.tools/api/topics.json

# 主题共现知识图谱
curl https://data.swarmlabs.tools/api/graph.json

需要按主题批量拉取、导出 BibTeX 或接入 AI Agent？查看 数据下载与格式 或 MCP 接入。